Add Inkling model support (#31681)

Co-authored-by: Chunan Zeng <zcnrex@gmail.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
Co-authored-by: Yanbin Jiang <jybsuper@gmail.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: Qiaolin Yu <qiaolin.yu@radixark.ai>
Co-authored-by: Zhichen Zeng <zczeng@uw.edu>
Co-authored-by: Aurick Qiao <aurick@thinkingmachines.ai>
Co-authored-by: Joseph <jk@thinkingmachines.ai>

python/sglang/test/kits/attention_unittest/runner_modes/cuda_graph_decode_runner.py

@@ -309,6 +309,7 @@ def _init_cuda_graph_replay_metadata(backend, capture_batch_size: int, batch):
         seq_lens_sum=batch.seq_lens_sum,
         seq_lens_cpu=batch.seq_lens_cpu,
         encoder_lens=batch.encoder_lens,
+        extend_seq_lens=getattr(batch, "extend_seq_lens", None),
         out_cache_loc=getattr(batch, "out_cache_loc", None),
         spec_info=batch.spec_info,
     )